{"id":"W4415226210","doi":"10.1016/j.cviu.2025.104529","title":"CCNeXt: An effective self-supervised stereo depth estimation approach","year":2025,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Epipolar geometry; Convolutional neural network; Feature (linguistics); Ground truth; Pixel; Stereopsis; Depth map; Feature extraction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000365608,0.0002674431,0.0002783387,0.0003939006,0.0005076493,0.001010745,0.0004858692,0.00006794379,0.000003983651],"category_scores_gemma":[0.00001874964,0.0002344465,0.00006735076,0.0005779137,0.00007861116,0.002579289,0.0005187884,0.0002142583,0.000008589755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002121156,"about_ca_system_score_gemma":0.00003345114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002821633,"about_ca_topic_score_gemma":6.974541e-7,"domain_scores_codex":[0.9982229,0.0001767233,0.0002836079,0.0007450357,0.0002365709,0.0003351608],"domain_scores_gemma":[0.998996,0.0001723718,0.00008168205,0.0005141385,0.00007244456,0.0001634016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002772316,0.0002361483,0.0001216367,0.000130584,0.00003749039,0.00002011229,0.001818121,0.0002171434,0.001477619,0.08330593,0.0007537585,0.9118537],"study_design_scores_gemma":[0.001146092,0.000187204,0.001130247,0.0001377662,0.00001156639,0.00002891347,0.0002876013,0.9807715,0.0003041954,0.01549824,0.0002394734,0.0002572029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001910665,0.000122612,0.9915486,0.0003425249,0.0003833141,0.0004230434,7.066327e-7,0.0005192158,0.004749319],"genre_scores_gemma":[0.3939691,0.00001821412,0.6052736,0.0006536269,0.00003098407,0.000007412589,0.000005427916,0.00001032313,0.00003129766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9805543,"threshold_uncertainty_score":0.9746637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02045026627220837,"score_gpt":0.3028070441034886,"score_spread":0.2823567778312802,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}